arXiv:2509.02815cs.ROcs.LG2025-09被引 7
一策驾驭50种机器人，零样本适配真实新机型
Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization
- 用改进的形态感知架构+极端形态随机化训练
- 掌控百万级机器人形态变体，零样本迁移至新机器人
- 适合做通用机器人控制或具身智能研究者
我们提出一种单一通用的运动策略，基于50种不同腿式机器人进行训练。通过结合改进的形态感知架构（URMAv2）与基于性能的极端形态随机化课程，该策略学会控制数百万种形态变体。该策略实现了对未见过的真实人形和四足机器人的零样本迁移。
原文摘要 · Abstract (English)
We present a single, general locomotion policy trained on a diverse collection of 50 legged robots. By combining an improved embodiment-aware architecture (URMAv2) with a performance-based curriculum for extreme Embodiment Randomization, our policy learns to control millions of morphological variations. Our policy achieves zero-shot transfer to unseen real-world humanoid and quadruped robots.
机器人控制通用策略零样本迁移
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。